mirrors/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-04-28 18:32:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat: add phase 1 mem client (#10629)

Browse Source 
Adding a client on top of https://github.com/openai/openai/pull/672176
This commit is contained in:
jif-oai
2026-02-04 17:59:36 +00:00
committed by GitHub
parent 71e63f8d10
commit e9335374b9
8 changed files with 498 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
codex-rs/codex-api/README.md
View File

@@ -29,4 +29,13 @@ The public interface of this crate is intentionally small and uniform:
- Output: `Vec<ResponseItem>`.
- `CompactClient::compact_input(&CompactionInput, extra_headers)` wraps the JSON encoding and retry/telemetry wiring.
- **Memory trace summarize endpoint**
- Input: `MemoryTraceSummarizeInput` (re-exported as `codex_api::MemoryTraceSummarizeInput`):
- `model: String`.
- `traces: Vec<MemoryTrace>`.
- `MemoryTrace` includes `id`, `metadata.source_path`, and normalized `items`.
- `reasoning: Option<Reasoning>`.
- Output: `Vec<MemoryTraceSummaryOutput>`.
- `MemoriesClient::trace_summarize_input(&MemoryTraceSummarizeInput, extra_headers)` wraps JSON encoding and retry/telemetry wiring.
All HTTP details (URLs, headers, retry/backoff policies, SSE framing) are encapsulated in `codex-api` and `codex-client`. Callers construct prompts/inputs using protocol types and work with typed streams of `ResponseEvent` or compacted `ResponseItem` values.